{"id":"W3082498369","doi":"10.1109/tpami.2020.3020800","title":"GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Artificial intelligence; Normal; Depth map; Metric (unit); Computer vision; Pixel; Surface (topology); Consistency (knowledge bases); Enhanced Data Rates for GSM Evolution; Artificial neural network; Boundary (topology); Algorithm; Mathematics; Image (mathematics); Geometry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001322182,0.0002149417,0.000298262,0.0002144488,0.0002867114,0.0001896424,0.0001777503,0.00002889237,0.00002810237],"category_scores_gemma":[0.00000558519,0.0001691067,0.0001025421,0.001406541,0.00004566635,0.0004000999,0.00000964301,0.0001856547,0.000003540734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001939406,"about_ca_system_score_gemma":0.00001261923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001308515,"about_ca_topic_score_gemma":0.0002189415,"domain_scores_codex":[0.9986618,0.00004626847,0.0003123157,0.0005287502,0.0002061847,0.0002447517],"domain_scores_gemma":[0.9992731,0.0001187348,0.0001207455,0.0002157314,0.00009803524,0.0001736567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001985075,0.0000263546,0.000550364,0.00001560048,0.0001025634,0.000002580736,0.000229327,0.4405006,0.00003082328,0.00001071239,0.00000980958,0.5585014],"study_design_scores_gemma":[0.0001800192,0.0003758295,0.001376641,0.00002099867,0.0001713292,0.000007135558,0.00004258543,0.9876762,0.009861719,0.00003392966,0.00004722478,0.0002063672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003873431,0.0001633429,0.9940382,0.001542522,0.00006705193,0.0002159359,0.0000224518,0.0000654796,0.00001153256],"genre_scores_gemma":[0.9448079,0.0001264396,0.05379333,0.001184321,0.00001871874,0.00001711561,0.000009072339,0.000009798798,0.00003328615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9409345,"threshold_uncertainty_score":0.6895971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02983077716167372,"score_gpt":0.2780307465243003,"score_spread":0.2481999693626265,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}